INDEX

Explanations

names of individuals and titles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.66

 Finlay

-0.64

ⓧ

-0.62

↵↵↵↵

-0.59

 llan

-0.58

BackStack

-0.57

BrowserRouter

-0.55

ConstraintMaker

-0.54

↵↵↵↵↵↵↵

-0.53

POSITIVE LOGITS

enerys

0.79

LOTTE

0.78

maries

0.77

Ann

0.77

 Maryam

0.74

netje

0.73

ourdes

0.71

vonne

0.71

ANN

0.70

ydd

0.70

Activations Density 0.377%

names of individuals and titles

No Comments

No Known Activations